{"id":"2b46c08d-4ddd-49f4-87f7-bac901d2384a","slug":"hf-model-pradheep1647-grpo-think-len-capped-linear-gndqya-15","name":"grpo-think-len-capped-linear","description":"Hugging Face model Pradheep1647/grpo-think-len-capped-linear. Library: peft. 25 downloads.","capabilities":["peft","safetensors","lora","grpo","trl","reasoning","length-penalty","dataset:openai/gsm8k","arxiv:2609.19969","base_model:Qwen/Qwen3-1.7B","base_model:adapter:Qwen/Qwen3-1.7B"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:10.839Z"}